Update model card with metrics

README.md

@@ -1,2 +1,71 @@
-# Control-LLM-Llama3.1-8B-Math16
-This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.
+---
+license: llama3.1
+datasets:
+- nvidia/OpenMathInstruct-2
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+model-index:
+- name: Control-LLM-Llama3.1-8B-Math16
+  results:
+  - task:
+      type: math-evaluation
+    dataset:
+      type: nvidia/OpenMathInstruct-2
+      name: OpenMathInstruct
+    metrics:
+    - name: exact_match,none
+      type: exact_match
+      value: 0.6327358367133324
+      stderr: 0.0052245703347459605
+      verified: false
+    - name: exact_match,none (gsm8k_0shot_instruct)
+      type: exact_match
+      value: 0.9052312357846853
+      stderr: 0.008067791560015407
+      verified: false
+    - name: exact_match,none (meta_math_0shot_instruct)
+      type: exact_match
+      value: 0.6276
+      stderr: 0.006837616441401548
+      verified: false
+    - name: exact_match,none (meta_math_hard_0shot_instruct)
+      type: exact_match
+      value: 0.3806646525679758
+      stderr: 0.013349170720370741
+      verified: false
+  - task:
+      type: original-capability
+    dataset:
+      type: meta/arc-dataset
+      name: Meta-ARC Dataset
+    metrics:
+    - name: exact_match,strict-match
+      type: exact_match
+      value: 0.5723263625528227
+      stderr: 0.002858377993520894
+      verified: false
+    - name: exact_match,strict-match (meta_arc_0shot_instruct)
+      type: exact_match
+      value: 0.7974248927038626
+      stderr: 0.01178043813618557
+      verified: false
+    - name: exact_match,strict-match (meta_gpqa_0shot_cot_instruct)
+      type: exact_match
+      value: 0.25223214285714285
+      stderr: 0.02054139101648797
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_0shot_instruct)
+      type: exact_match
+      value: 0.6837345107534539
+      stderr: 0.0039243761987253515
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_instruct)
+      type: exact_match
+      value: 0.4324301861702128
+      stderr: 0.004516653585262379
+      verified: false
+---
+# Control-LLM-Llama3.1-8B-Math16
+This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.